From c463f451a73a2fbcf4b5e42766609fdb42467582 Mon Sep 17 00:00:00 2001
From: Juan Quintela <quintela@redhat.com>
Date: Mon, 22 Nov 2010 15:57:06 -0200
Subject: [PATCH 2/6] KVM don't care about TLB handling

RH-Author: Juan Quintela <quintela@redhat.com>
Message-id: <4bd25f6cc4cdbc623bb1e968af8f846f148b1c72.1290441250.git.quintela@redhat.com>
Patchwork-id: 13776
O-Subject: [PATCH 2/6] KVM don't care about TLB handling
Bugzilla: 513765 589017
RH-Acked-by: Glauber Costa <glommer@redhat.com>
RH-Acked-by: Jes Sorensen <Jes.Sorensen@redhat.com>
RH-Acked-by: Alex Williamson <alex.williamson@redhat.com>
RH-Acked-by: Avi Kivity <avi@redhat.com>

TLB handling is only used in TCG mode.  It is very costly for guests with lots
of memory ad lots of CPU's.

Signed-off-by: Juan Quintela <quintela@redhat.com>
---
 qemu/exec.c |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
---
 qemu/exec.c |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/qemu/exec.c b/qemu/exec.c
index cf5a859..37bcc7a 100644
--- a/qemu/exec.c
+++ b/qemu/exec.c
@@ -1866,6 +1866,9 @@ void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
     for(i = 0; i < len; i++)
         p[i] &= mask;
 
+    if (kvm_enabled())
+        return;
+
     /* we modify the TLB cache so that the dirty bit will be set again
        when accessing the range */
     start1 = start + (unsigned long)phys_ram_base;
-- 
1.7.3.2